nsaspy/prolog-rlm

[P0] Build opaque external context store and context operations #6

New issue

Closed

opened 2026-08-12 01:17:52 +00:00 by lost-rob0t · 0 comments

lost-rob0t commented

2026-08-12 01:17:52 +00:00

(Migrated from github.com)

Goal

Keep large inputs outside the root model prompt while exposing controlled, inspectable operations over them.

Scope

define opaque context handles and metadata terms;
support text/term-backed contexts initially;
implement peek/slice/search/partition/map/reduce primitives;
bound result sizes and execution time;
make context operations traceable;
prevent arbitrary filesystem/network access through context handles;
define extension points for larger persistent stores later.

Acceptance criteria

a context significantly larger than the model prompt can be registered and queried by handle;
root model receives metadata/handles rather than the full payload;
search and partition results are bounded;
invalid/stale handles produce structured errors;
context operations emit trace events with bytes/items inspected.

Dependencies

#4
parent #3

Research

See RLM-RESEARCH-002-agentic-harness.org and RLM-RESEARCH-009-durable-artifact-context.org.

## Goal Keep large inputs outside the root model prompt while exposing controlled, inspectable operations over them. ## Scope - define opaque context handles and metadata terms; - support text/term-backed contexts initially; - implement peek/slice/search/partition/map/reduce primitives; - bound result sizes and execution time; - make context operations traceable; - prevent arbitrary filesystem/network access through context handles; - define extension points for larger persistent stores later. ## Acceptance criteria - a context significantly larger than the model prompt can be registered and queried by handle; - root model receives metadata/handles rather than the full payload; - search and partition results are bounded; - invalid/stale handles produce structured errors; - context operations emit trace events with bytes/items inspected. ## Dependencies - #4 - parent #3 ## Research See `RLM-RESEARCH-002-agentic-harness.org` and `RLM-RESEARCH-009-durable-artifact-context.org`.

nsaspy referenced this issue from a pull request that will close it,

2026-08-27 20:01:59 +00:00

Build opaque bounded external context runtime (#6) #25

nsaspy referenced this issue

2026-08-27 20:02:18 +00:00

Add deterministic skill-selection evaluation metrics #251

nsaspy referenced this issue from a commit

2026-09-02 17:46:00 +00:00

Merge current main provider behavior into #6 context branch

nsaspy referenced this issue

2026-09-08 01:29:18 +00:00

[MACHINE-SPIRIT 7/8] Meta-reasoning and bounded self-improvement: failure learning, strategy evolution, rule promotion, self-model and expert synthesis #394

nsaspy referenced this issue

2026-09-08 01:29:18 +00:00

[MACHINE-SPIRIT 5/8] Durable world-model architecture: event sourcing, append-only semantics, incremental inference, identity and ontology evolution #396

nsaspy referenced this issue

2026-09-08 01:29:19 +00:00

[MACHINE-SPIRIT 4/8] Procedural intelligence and expert systems: production rules, blackboards, HTN planning, CBR, diagnosis and repair #397

nsaspy referenced this issue

2026-09-08 01:29:19 +00:00

[MACHINE-SPIRIT 3/8] Epistemics and truth maintenance: belief revision, ATMS/TMS, paraconsistency, defaults, provenance, temporal truth #398

nsaspy referenced this issue

2026-09-08 01:46:57 +00:00

[EPIC][library/tool] General semantic knowledge compiler: arbitrary natural language → extensible validated symbolic knowledge #410

nsaspy referenced this issue

2026-09-08 01:47:35 +00:00

[MACHINE-SPIRIT 1/8] Knowledge-representation foundations: logic, frames, DL/Datalog, events, typed open vocabularies #400

nsaspy referenced this issue

2026-09-08 01:47:35 +00:00

[MACHINE-SPIRIT 1/8] Knowledge-representation foundations: logic, frames, DL/Datalog, events, typed open vocabularies #400

nsaspy referenced this issue

2026-09-08 01:47:43 +00:00

[MACHINE-SPIRIT 3/8] Epistemics and truth maintenance: belief revision, ATMS/TMS, paraconsistency, defaults, provenance, temporal truth #398

nsaspy referenced this issue

2026-09-08 01:47:43 +00:00

[MACHINE-SPIRIT 3/8] Epistemics and truth maintenance: belief revision, ATMS/TMS, paraconsistency, defaults, provenance, temporal truth #398

nsaspy referenced this issue

2026-09-08 01:47:43 +00:00

[MACHINE-SPIRIT 3/8] Epistemics and truth maintenance: belief revision, ATMS/TMS, paraconsistency, defaults, provenance, temporal truth #398

nsaspy referenced this issue

2026-09-08 01:47:46 +00:00

[MACHINE-SPIRIT 4/8] Procedural intelligence and expert systems: production rules, blackboards, HTN planning, CBR, diagnosis and repair #397

nsaspy referenced this issue

2026-09-08 01:47:47 +00:00

[MACHINE-SPIRIT 4/8] Procedural intelligence and expert systems: production rules, blackboards, HTN planning, CBR, diagnosis and repair #397

nsaspy referenced this issue

2026-09-08 01:47:47 +00:00

[MACHINE-SPIRIT 4/8] Procedural intelligence and expert systems: production rules, blackboards, HTN planning, CBR, diagnosis and repair #397

nsaspy referenced this issue

2026-09-08 01:47:50 +00:00

[MACHINE-SPIRIT 5/8] Durable world-model architecture: event sourcing, append-only semantics, incremental inference, identity and ontology evolution #396

nsaspy referenced this issue

2026-09-08 01:47:53 +00:00

[MACHINE-SPIRIT 6/8] Retrieval and symbolic attention: bounded projection, graph search, relevance, embeddings as sensors, working-memory control #395

nsaspy referenced this issue

2026-09-08 01:47:56 +00:00

[MACHINE-SPIRIT 7/8] Meta-reasoning and bounded self-improvement: failure learning, strategy evolution, rule promotion, self-model and expert synthesis #394

nsaspy referenced this issue

2026-09-08 01:47:56 +00:00

[MACHINE-SPIRIT 7/8] Meta-reasoning and bounded self-improvement: failure learning, strategy evolution, rule promotion, self-model and expert synthesis #394

nsaspy referenced this issue

2026-09-08 01:47:56 +00:00

[MACHINE-SPIRIT 7/8] Meta-reasoning and bounded self-improvement: failure learning, strategy evolution, rule promotion, self-model and expert synthesis #394

nsaspy referenced this issue

2026-09-08 01:47:59 +00:00

[MACHINE-SPIRIT 8/8] Adversarial synthesis: Machine Spirit v1 architecture, conformance suite, zero-LLM demonstrations, and implementation graph #393

nsaspy referenced this issue

2026-09-10 21:18:00 +00:00

[EPIC] Agentic Prolog RLM v0.1 #424

Sign in to join this conversation.

No labels

good first issue

No milestone

No project

No assignees

1 participant

Notifications

Due date

The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference

nsaspy/prolog-rlm#6

No description provided.